def test(self, e):
k = 3
# read files and turn it into a sentences x words matrix
matrix = {}
for idx in range(len(e.sentences)):
matrix[idx] = {}
words = re.split('\W+', e.sentences[idx])
for word in words:
if len(word) == 0: # skip ""
continue
if word not in matrix[idx]:
matrix[idx][word] = 0
matrix[idx][word] += 1
# complete svd here
arr = pd.DataFrame.from_dict(matrix).fillna(0).values
# u, s, vh = np.linalg.svd(arr, full_matrices=True) # full matrix
u, s, vh = np.linalg.svd(arr, full_matrices=False) # reduced matrix
# print u.shape
# print s.shape
# print vh.shape
# print np.allclose(arr, np.dot(u * s, vh))
# print vh[:, k]
threshold = 0.5
sigma_threshold = max(s) * threshold
s[s < sigma_threshold] = 0 # Set all other singular values to zero
saliency_vec = np.dot(
np.square(s), np.square(vh)
) # Build a "length vector" containing the length (i.e. saliency) of each sentence
top_sentences = saliency_vec.argsort()[-k:][::-1]
top_sentences.sort(
) # Return the sentences in the order in which they appear in the document
pred = [e.sentences[i] for i in top_sentences]
# print pred
evaluate = Evaluator()
[P_1, R_1, F1_1] = evaluate.ROUGE1(pred=(pred), test=(e.ground_truths))
[P_2, R_2, F1_2] = evaluate.ROUGE2(pred=(pred), test=(e.ground_truths))
return P_1, R_1, F1_1, P_2, R_2, F1_2
